List of Publications: Google Scholar, DBLP

My research has been supported by NSF grants NSF-SES 2218975, NSF-IIS 0844935 and BCS-CDI-Type I 1027801, Google, and Microsoft.

Current Projects:

Explainable Rankings: Towards Explainable and Transparent Ranking Functions
    • Explaining Ranking Functions (VLDB’20, EARS’19)
    • Disparity Compensation for Fair Ranking (ICDE’24)
TRANSPARENT AND ACCOUNTABLE DECISION SYSTEMS
    • Algorithmic Transparency and Accountability through Crowdsourcing (FAccT’23)

NSF MCA Grant Award for the proposal: “Transparent and Accountable Decision Systems“. (July 2022)

TRUSTWORTHY AND TRANSPARENT DEMOCRACY
    • Identifying Possible Winners in Ranked Choice Voting Elections with Outstanding Ballots (HCOMP’22)
 

Past Projects:

DIGITALSELF: PERSONAL INFORMATION MANAGEMENT
    • Integration and Exploration of Connected Personal Digital Traces ( CHIIR’23, ICWSM’22, BPM’19, CIKM’18 Demo, ExploreDB’17, ODBASE’17)
    • Personal Data Extraction (IIWeb’14)
    • Context-aware Personal Information Search (HICSS’22, ASIS&T’19)

Google Research Award, Remembrance of Data Past: Using Context in Personal Information Search, with Thu D. Nguyen (July 2012).

DECENTRALIZED COLLABORATIVE FILTERING: PRIVACY-AWARE PERSONAL RECOMMENDATIONS
    • Federated collaborative transfer for recommendation (SIGIR’21)
    • Fairness-Aware Group recommendations (RecSys’22)
RelaxedQ: Semi-structured Data Scoring:

Scoring mechanisms to rank (approximate) structural matches to semi-structured data queries, and efficient algorithms to identify the best structural matches.

    • In Personal Information Management Systems (TKDE’12, EDBT’11, IEEE DEB’09, EDBT’08, ICDE’08 demo)
    • For XML Data (VLDB ’05)

NSF CAREER Award for the proposal: “Relaxed Content and Structure Queries over Heterogeneous Data”. (July 2009)

PERSEUS: Patient Emotion and stRucture SEarch USer interface
    • Patient Forum Search (ICWSM’14, CIKM’13)

NSF CDI-Type I Grant “Gaining Knowledge from Other Patients: Structuring and Searching the content of Health-Related Web Posts” (October 2010). <!–(Rutgers Focus and Daily Targum articles)–>
Google Research Award for the proposal: “PERSEUS: Structuring and Searching the Content of Health-Related Web Posts,” joint with Noémie Elhadad, Columbia Biomedical Informatics. (April 2010)

Data Corroboration:
    • Over Web Sources (EDBT’14, IS’11,WebDB’07)
    • In Join Queries (VLDB ’10)
    • Over Disagreeing Views (WSDM’10)
    • For Data Cleaning (CleanDB’06)

Microsoft Live Labs Search Award for the research proposal “The Truth Is out There: Aggregating Answers From Multiple Web Sources.“

URSA: User Reviews Structure Analysis
    • Over a Restaurant Review Data Set (IS 2013, WebDB’09)

Google Research Award for the proposal:  “URSA: Understanding User Reviewing Patterns,” joint with Noémie Elhadad, Columbia Biomedical Informatics.

XML Projection:

A projection operator integrated in the Galax XQuery implementation project (VLDB’03 paper and Demo)

XML Version Management:

A change-centric model and diff tools (XyDiff) to identify and represent changes in XML documents. (VLDB’01, ICDE’02, BDA’00, BDA’01) 

Top-k Query Processing:

Adaptive algorithms to efficiently identify a query’s top-k matching objects, for different scenarios (multimedia, web services, XML). (TKDE’04,TODS’04, ICDE’02)